Electroluminescence (EL) imaging is a widely adopted method in quality assurance of the photovoltaic (PV) manufacturing industry. With the growing demand for high-quality PV products, automatic inspection methods based on machine vision have become an emerging area concern to replace manual inspectors. Therefore, this paper presents an automatic defect-inspection method for multi-cell monocrystalline PV modules with EL images. A processing routine is designed to extract the defect features of the PV module, eliminating the influence of the intrinsic structural features. Spectrum domain analysis is applied to effectively reconstruct an improved PV layout from a defective one by spectrum filtering in a certain direction. The reconstructed image is used to segment the PV module into cells and slices. Based on the segmentation, defect detection is carried out on individual cells or slices to detect cracks, breaks, and speckles. Robust performance has been achieved from experiments on many samples with varying illumination conditions and defect shapes/sizes, which shows the proposed method can efficiently distinguish intrinsic structural features from the defect features, enabling precise and speedy defect detections on multi-cell PV modules.
Robotics is widely used in nearly all sorts of manufacturing. Steady performance and accurate movement of robotics are vital in quality control. Along with the coming of the Industry 4.0 era, oceans of sensor data from robotics are available, within which the health condition and faults are enclosed. Considering the growing complexity of the manufacturing system, an automatic and intelligent health-monitoring system is required to detect abnormalities of robotics in real-time to promote quality and reduce safety risks. Therefore, in this study, we designed a novel semantic-based modeling method for multistage robotic systems. Experiments show that sole modeling is not sufficient for multiple stages. We propose a descriptor to conclude the stages of robotic systems by learning from operational data. The descriptors are akin to a vocabulary of the systems; hence, semantic checking can be carried out to monitor the correctness of operations. Furthermore, the stage classification and its semantics were used to apply various regression models to each stage to monitor the quality of each operation. The proposed method was applied to a photovoltaic manufacturing system. Benchmarks on production datasets from actual factories show the effectiveness of the proposed method to realize an AI-enabled real-time health-monitoring system of robotics.
29 August 2024 in IEEE Transactions on Instrumentation and Measurement
In camera distortion correction and calibration research, there is a prevalent assumption that distortion exhibits radial symmetry around a center of distortion. However, the validity of this assumption is contingent upon the extent of tangential distortion in the system. This study delves into a quantitative analysis of tangential distortion by simulating diverse camera specifications and tilt angles between lenses and sensor arrays. The findings indicate that larger field-of-view and smaller pixel sizes lead to an augmentation of tangential distortion. In practical camera settings, the tangential distortion can extend beyond a dozen pixels. Consequently, traditional models relying on radial symmetry may encounter a decline in precision when addressing such distortions. Moreover, the study suggests that centers of distortion determined geometrically based on radial symmetry may not be numerically optimal in scenarios with tangential distortions. As a result, the robustness of the radial symmetry assumption may be compromised in the face of prominent trends in camera advancements.
26 October 2026 in Measurement Science and Technology
In heavy-duty shipbuilding, the efficient transfer of ship blocks directly affects the overall construction schedule, while reliable identification of the lifting and dropping states of transport vehicles is essential for updating block locations. However, vehicle vibration, road disturbances, and local sensor anomalies can cause substantial fluctuations in multi-source measurement signals, limiting the recognition accuracy of conventional hard-threshold methods. To address this issue, a knowledge-driven dual-expert machine learning framework with physical gating is proposed. The standard deviation of vehicle speed is used as the physical gating indicator to partition and route data under different operating conditions. A 16-dimensional domain-informed hybrid feature space is then constructed, and LightGBM and CatBoost are employed as the steady-state and dynamic experts, respectively. Experiments on real-world engineering data show that the proposed method achieves a Macro-F1 of 0.9938 and an Accuracy of 0.9972. Measurement-noise enhancement experiments and tests on unseen vehicles with different rated tonnages further demonstrate its robustness and cross-vehicle generalization capability. t-SNE and SHAP analyses reveal distinct feature dependencies between the two experts, which are generally consistent with the physical mechanisms of lifting operations and driving disturbances. The proposed method provides an effective approach for reliable operational-state measurement of heavy-duty engineering vehicles under complex operating conditions.
Electroluminescence (EL) imaging is a widely adopted method in quality assurance of photovoltaic (PV) manufacturing industry. With the growing demand for high quality PV products, automatic inspection method based on machine vision has become an emerging concern to replace manual inspectors. Hereby, this paper presents automatic defect inspection method for multi-cell monocrystalline PV module with EL images. A processing routine is designed to extract defect features while eliminating the influence of the intrinsic structural features of the PV module. The spectrum domain analysis is applied to effectively reconstruct a perfect PV module layout from a defective one by spectrum filtering in certain direction in the frequency domain. The reconstructed image could then be used to segment the PV module into cells and slices. Based on the segmentation, defect detection can be carried out on individual cells or slices to detect cracks, breaks, and speckles. Robust performance is exhibited form experiments on many samples with varying illumination condition and defect shape/size, which shows the method can efficiently distinguish intrinsic structural features from the defect features, hence enables precise and speedy defect detection on multi-cell PV modules.